)]}' { "log": [ { "commit": "cafcfcaa60dbb5bcccbbc1d0ad7d4bdeeb4d0cc8", "tree": "a3830f77e0d4de4393ce02fefe401a2edead8746", "parents": [ "3cf0f4ece9f1680e54b154b1e38baaf6ace20a62" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:45 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:53 2006 -0800" }, "message": "[PATCH] sh: task_thread_info()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3cf0f4ece9f1680e54b154b1e38baaf6ace20a62", "tree": "eaebb77428101f5093aa7c0fa8cbc008c9d61ba2", "parents": [ "26ecbdea4bf46b0165db4aafd8e4981b4db53936" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:44 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:52 2006 -0800" }, "message": "[PATCH] sh: task_pt_regs()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "26ecbdea4bf46b0165db4aafd8e4981b4db53936", "tree": "16d743692c32f465a5c73b3f051bd87c87ba08ae", "parents": [ "ee3eea165e706a3ce8a53693e810403f65239ebb" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:43 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:52 2006 -0800" }, "message": "[PATCH] sparc64: task_pt_regs()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ee3eea165e706a3ce8a53693e810403f65239ebb", "tree": "6e2b4a23cac74a3fadf180d25720eb39292a12e6", "parents": [ "f3169641c12d2c5abdab863f5393a3f3534788dd" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:43 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:52 2006 -0800" }, "message": "[PATCH] sparc64: task_stack_page()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f3169641c12d2c5abdab863f5393a3f3534788dd", "tree": "a455f38f7ac748c3e334d1105d16a0f94a4c0e57", "parents": [ "65e0fdffc977e69a8f1f26d4bf8ba30984db7e44" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:42 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:52 2006 -0800" }, "message": "[PATCH] sparc64: task_thread_info()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "65e0fdffc977e69a8f1f26d4bf8ba30984db7e44", "tree": "569c7238ea64dfac7508c503d4f0229a72d06e32", "parents": [ "07b047fc2466249aff7cdb23fa0b0955a7a00d48" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:41 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:52 2006 -0800" }, "message": "[PATCH] i386: task_stack_page()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "07b047fc2466249aff7cdb23fa0b0955a7a00d48", "tree": "af22cc80470f8aff6d0c25276ef8fae2b3f537a7", "parents": [ "06b425d80f56280e698b3e8487c372e0d39d9ba1" ], "author": { "name": "akpm@osdl.org", "email": "akpm@osdl.org", "time": "Thu Jan 12 01:05:41 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:52 2006 -0800" }, "message": "[PATCH] i386: fix task_pt_regs()\n\n\r)\n\nFrom: Al Viro \u003cviro@ftp.linux.org.uk\u003e\n\ntask_pt_regs() needs the same offset-by-8 to match copy_thread()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "06b425d80f56280e698b3e8487c372e0d39d9ba1", "tree": "107f441a080074b5fdc16cf4d94632356b29a1e5", "parents": [ "57eafdc22c8e788859b67c2c7ac4d636716603a5" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:40 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:51 2006 -0800" }, "message": "[PATCH] i386: task_thread_info()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "57eafdc22c8e788859b67c2c7ac4d636716603a5", "tree": "a85b01c191084bfc0809d8704e58c2602fa5fddd", "parents": [ "bb049232fa8fe08c90b182f378eed5017da5235c" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:39 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:51 2006 -0800" }, "message": "[PATCH] amd64: task_stack_page()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bb049232fa8fe08c90b182f378eed5017da5235c", "tree": "b8a71968d4acedf35081986584c6f24c21c68b65", "parents": [ "e4f17c436f8e4241995c2531372be8dd7ea6ff75" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:38 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:51 2006 -0800" }, "message": "[PATCH] amd64: task_pt_regs()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e4f17c436f8e4241995c2531372be8dd7ea6ff75", "tree": "ac797b8402c9a44182f16b76ffc13559d6c0edb3", "parents": [ "e52f4ca2a7cfea3495cabae23d48f1538f09ccf2" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:38 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:51 2006 -0800" }, "message": "[PATCH] amd64: task_thread_info()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e52f4ca2a7cfea3495cabae23d48f1538f09ccf2", "tree": "d924a14c6e64a768faf98eb19deb5b7e81ca9934", "parents": [ "27f451304aa6f2bccf34ef3c2b049c01d05d6fff" ], "author": { "name": "akpm@osdl.org", "email": "akpm@osdl.org", "time": "Thu Jan 12 01:05:37 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:50 2006 -0800" }, "message": "[PATCH] alpha: task_pt_regs()\n\n\r)\n\nFrom: Al Viro \u003cviro@ftp.linux.org.uk\u003e\n\nrename alpha_task_regs() to task_pt_regs(), switch open-coded instances\nto use of the helper.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "27f451304aa6f2bccf34ef3c2b049c01d05d6fff", "tree": "f4593b303847acb33885ea2638c5ef96a82945dd", "parents": [ "37bfbaf995d2c1f8196ee04c9d6f68258d5ec3e8" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:36 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:50 2006 -0800" }, "message": "[PATCH] alpha: task_stack_page()\n\nuse task_stack_page() for accesses to stack page of task in alpha-specific\nparts of tree\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "37bfbaf995d2c1f8196ee04c9d6f68258d5ec3e8", "tree": "baa1ce07e948e5b91cfb3cd5d139f8d45e1ba325", "parents": [ "9fc658763bf992e778243ebe898b03746151ab88" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jan 12 01:05:36 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:50 2006 -0800" }, "message": "[PATCH] alpha: task_thread_info()\n\nuse task_thread_info() for accesses to thread_info of task in arch/alpha\nand include/asm-alpha\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "198e2f181163233b379dc7ce8a6d7516b84042e7", "tree": "cc4067ca1c81034ba8d214b7ff4c39f2f5be66ee", "parents": [ "4dc7a0bbeb6882ad665e588e82fabe5bb4645f2f" ], "author": { "name": "akpm@osdl.org", "email": "akpm@osdl.org", "time": "Thu Jan 12 01:05:30 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:50 2006 -0800" }, "message": "[PATCH] scheduler cache-hot-autodetect\n\n\r)\n\nFrom: Ingo Molnar \u003cmingo@elte.hu\u003e\n\nThis is the latest version of the scheduler cache-hot-auto-tune patch.\n\nThe first problem was that detection time scaled with O(N^2), which is\nunacceptable on larger SMP and NUMA systems. To solve this:\n\n- I\u0027ve added a \u0027domain distance\u0027 function, which is used to cache\n measurement results. Each distance is only measured once. This means\n that e.g. on NUMA distances of 0, 1 and 2 might be measured, on HT\n distances 0 and 1, and on SMP distance 0 is measured. The code walks\n the domain tree to determine the distance, so it automatically follows\n whatever hierarchy an architecture sets up. This cuts down on the boot\n time significantly and removes the O(N^2) limit. The only assumption\n is that migration costs can be expressed as a function of domain\n distance - this covers the overwhelming majority of existing systems,\n and is a good guess even for more assymetric systems.\n\n [ People hacking systems that have assymetries that break this\n assumption (e.g. different CPU speeds) should experiment a bit with\n the cpu_distance() function. Adding a -\u003emigration_distance factor to\n the domain structure would be one possible solution - but lets first\n see the problem systems, if they exist at all. Lets not overdesign. ]\n\nAnother problem was that only a single cache-size was used for measuring\nthe cost of migration, and most architectures didnt set that variable\nup. Furthermore, a single cache-size does not fit NUMA hierarchies with\nL3 caches and does not fit HT setups, where different CPUs will often\nhave different \u0027effective cache sizes\u0027. To solve this problem:\n\n- Instead of relying on a single cache-size provided by the platform and\n sticking to it, the code now auto-detects the \u0027effective migration\n cost\u0027 between two measured CPUs, via iterating through a wide range of\n cachesizes. The code searches for the maximum migration cost, which\n occurs when the working set of the test-workload falls just below the\n \u0027effective cache size\u0027. I.e. real-life optimized search is done for\n the maximum migration cost, between two real CPUs.\n\n This, amongst other things, has the positive effect hat if e.g. two\n CPUs share a L2/L3 cache, a different (and accurate) migration cost\n will be found than between two CPUs on the same system that dont share\n any caches.\n\n(The reliable measurement of migration costs is tricky - see the source\nfor details.)\n\nFurthermore i\u0027ve added various boot-time options to override/tune\nmigration behavior.\n\nFirstly, there\u0027s a blanket override for autodetection:\n\n\tmigration_cost\u003d1000,2000,3000\n\nwill override the depth 0/1/2 values with 1msec/2msec/3msec values.\n\nSecondly, there\u0027s a global factor that can be used to increase (or\ndecrease) the autodetected values:\n\n\tmigration_factor\u003d120\n\nwill increase the autodetected values by 20%. This option is useful to\ntune things in a workload-dependent way - e.g. if a workload is\ncache-insensitive then CPU utilization can be maximized by specifying\nmigration_factor\u003d0.\n\nI\u0027ve tested the autodetection code quite extensively on x86, on 3\nP3/Xeon/2MB, and the autodetected values look pretty good:\n\nDual Celeron (128K L2 cache):\n\n ---------------------\n migration cost matrix (max_cache_size: 131072, cpu: 467 MHz):\n ---------------------\n [00] [01]\n [00]: - 1.7(1)\n [01]: 1.7(1) -\n ---------------------\n cacheflush times [2]: 0.0 (0) 1.7 (1784008)\n ---------------------\n\nHere the slow memory subsystem dominates system performance, and even\nthough caches are small, the migration cost is 1.7 msecs.\n\nDual HT P4 (512K L2 cache):\n\n ---------------------\n migration cost matrix (max_cache_size: 524288, cpu: 2379 MHz):\n ---------------------\n [00] [01] [02] [03]\n [00]: - 0.4(1) 0.0(0) 0.4(1)\n [01]: 0.4(1) - 0.4(1) 0.0(0)\n [02]: 0.0(0) 0.4(1) - 0.4(1)\n [03]: 0.4(1) 0.0(0) 0.4(1) -\n ---------------------\n cacheflush times [2]: 0.0 (33900) 0.4 (448514)\n ---------------------\n\nHere it can be seen that there is no migration cost between two HT\nsiblings (CPU#0/2 and CPU#1/3 are separate physical CPUs). A fast memory\nsystem makes inter-physical-CPU migration pretty cheap: 0.4 msecs.\n\n8-way P3/Xeon [2MB L2 cache]:\n\n ---------------------\n migration cost matrix (max_cache_size: 2097152, cpu: 700 MHz):\n ---------------------\n [00] [01] [02] [03] [04] [05] [06] [07]\n [00]: - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1)\n [01]: 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1)\n [02]: 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1)\n [03]: 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1)\n [04]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1)\n [05]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1)\n [06]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1)\n [07]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) -\n ---------------------\n cacheflush times [2]: 0.0 (0) 19.2 (19281756)\n ---------------------\n\nThis one has huge caches and a relatively slow memory subsystem - so the\nmigration cost is 19 msecs.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Ashok Raj \u003cashok.raj@intel.com\u003e\nSigned-off-by: Ken Chen \u003ckenneth.w.chen@intel.com\u003e\nCc: \u003cwilder@us.ibm.com\u003e\nSigned-off-by: John Hawkes \u003chawkes@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4dc7a0bbeb6882ad665e588e82fabe5bb4645f2f", "tree": "8c034f802157d7f449e76f45086c0e13e0ea4711", "parents": [ "c6b44d10f25e5a93eca5135b686a35775c63546e" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jan 12 01:05:27 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Jan 12 09:08:49 2006 -0800" }, "message": "[PATCH] sched: add cacheflush() asm\n\nAdd per-arch sched_cacheflush() which is a write-back cacheflush used by\nthe migration-cost calibration code at bootup time.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "983d5dbdb2b38d024935f560a91cddcf704875f3", "tree": "834cda0f26f3902aea74d1cd81a9202f78cc5f14", "parents": [ "0d9cb75f2f41788a59bcd3dac30b264a4bebaf2e" ], "author": { "name": "Vivek Goyal", "email": "vgoyal@in.ibm.com", "time": "Thu Jan 12 03:35:20 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:09:58 2006 -0800" }, "message": "[PATCH] x86_64: Fix SMP bootup with CONFIG_KDUMP enabled\n\no This fix was posted for i386 long back. Posting it for x86_64.\n\n http://marc.theaimsgroup.com/?l\u003dlinux-kernel\u0026m\u003d110380103229830\u0026w\u003d2\n\no This patch fixes the problem of secondary cpus boot up. This situation\n is faced when kernel is built for default locations like 16MB and\n onwards. In this configuration, only primary cpu (BP) comes and\n secondary cpus don\u0027t boot.\n\no Problem occurs because in trampoline code, lgdt is not able to load the\n GDT as it happens to be situated beyond 16MB. This is due to the fact\n that cpu is still in real mode and default operand size is 16bit.\n\no This patch uses lgdtl instead of lgdt to force operand size to 32\n instead of 16.\n\nSigned-off-by: Vivek Goyal \u003cvgoyal@in.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "0d9cb75f2f41788a59bcd3dac30b264a4bebaf2e", "tree": "a7e6b5a6bef3c849b95d5535e6e20858e5063038", "parents": [ "256ddb01ebdcb065f81487fff00be833192d8764" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:47:10 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:04 2006 -0800" }, "message": "[PATCH] x86_64: Don\u0027t confuse noapic with noapictimer\n\nHandling common prefixes is tricky.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "256ddb01ebdcb065f81487fff00be833192d8764", "tree": "203b5e3ab397ccc48cb62e2fb4801f6f3d15bd19", "parents": [ "2a2d5924c249e0f73aa00d617f8d5e242ea1430d" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:47:07 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:04 2006 -0800" }, "message": "[PATCH] x86_64: don\u0027t copy command line twice\n\n... reducing the amount of changes Xen has to do.\n\nSigned-Off-By: Jan Beulich \u003cjbeulich@novell.com\u003e\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2a2d5924c249e0f73aa00d617f8d5e242ea1430d", "tree": "2458187ff2b5eea03f269e15acf3532f351f8fcb", "parents": [ "4092bdebab46235d69fcd68afc710cddad550892" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:47:03 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:04 2006 -0800" }, "message": "[PATCH] i386/x86-64: make setup_early_printk() usage consistent\n\nThe explicit and implicit calls to setup_early_printk() were passing\ninconsistent arguments.\n\nSigned-Off-By: Jan Beulich \u003cjbeulich@novell.com\u003e\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4092bdebab46235d69fcd68afc710cddad550892", "tree": "fafc19afdec2d7706444efde462dbefc6c06c0e8", "parents": [ "6c5acd160a10c76e8debf4f8fa8256d7c914f290" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:47:00 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:04 2006 -0800" }, "message": "[PATCH] i386: Move DOUBLEFAULT config to arch/i386/Kconfig\n\nIt has no business being elsewhere and x86-64 doesn\u0027t need/want it.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6c5acd160a10c76e8debf4f8fa8256d7c914f290", "tree": "c13c1d282ad2bce8a6556d5d517879bf5b4343c7", "parents": [ "0a9c3ee7692fa20670986bcf550950e88ab9b4cc" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:57 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:03 2006 -0800" }, "message": "[PATCH] x86_64: Allow kernel page tables upto the end of memory\n\nPreviously they would be only allocated before the kernel text at\n1MB. This limited the maximum supported memory to 128GB.\nNow allow the e820 allocator to put them everywhere. Try\nto put them beyond any DMA zones to avoid filling them up.\nThis should free some GFP_DMA memory compared to earlier kernels.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "0a9c3ee7692fa20670986bcf550950e88ab9b4cc", "tree": "62721a6246e5b60a4a7ee779d82bf3b88a0896e6", "parents": [ "11a8e778c46ee76fc46b0a7fa9d455b5a8e3e19f" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:54 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:03 2006 -0800" }, "message": "[PATCH] x86_64: Use safe_smp_processor_id in MCE handler\n\nhard_smp_processor_id would return the local APIC id instead\nof the Linux processor id. On big systems they are often\nnot identical. safe_smp_processor_id is just a wrapper\naround it that does the necessary conversions.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "11a8e778c46ee76fc46b0a7fa9d455b5a8e3e19f", "tree": "2e6d19e5fbb9d686448868bc087673e696b5b4be", "parents": [ "5f1d189f8a87930d62c507800a8ac20b9a185e41" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:51 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:03 2006 -0800" }, "message": "[PATCH] x86_64: Some housekeeping in local APIC code\n\nRemove support for obsolete hardware and cleanup.\n\n- Remove checks for non integrated APICs\n- Replace apic_write_around with apic_write.\n- Remove apic_read_around\n- Remove APIC version reads used by old workarounds\n- Remove old workaround for Simics\n- Fix indentation\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "5f1d189f8a87930d62c507800a8ac20b9a185e41", "tree": "f83f756d8481dafe3b8ddba5b741ec6b5cf33e96", "parents": [ "1b2f6304500930ab534a6aa3198bce0c51586206" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:46:48 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:03 2006 -0800" }, "message": "[PATCH] x86_64: Display meaningful part of filename during BUG()\n\nWhen building in a separate objtree, file names produced by BUG() \u0026 Co. can\nget fairly long; printing only the first 50 characters may thus result in\n(almost) no useful information. The following change makes it so that rather\nthe last 50 characters of the filename get printed.\n\nSigned-Off-By: Jan Beulich \u003cjbeulich@novell.com\u003e\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1b2f6304500930ab534a6aa3198bce0c51586206", "tree": "208a8544004b6b60ab75fb7037a72b1fb4a21793", "parents": [ "5329e13d0bd82e13814050eb9facb25eedde4bbc" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:46:45 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:03 2006 -0800" }, "message": "[PATCH] x86_64: Reduce screen space needed by stack trace\n\nEspecially under Xen, where the console cannot be adjusted to more than 25\nlines, it is fairly important that the information displayed during a panic\nis as compact as possible. Below adjustments work towards that.\n\nSigned-Off-By: Jan Beulich \u003cjbeulich@novell.com\u003e\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "5329e13d0bd82e13814050eb9facb25eedde4bbc", "tree": "ec62d8058882edc85caaab3559a85ac1ffa30bf8", "parents": [ "bdf2b1c9fedf76a1797216559f221e5eaa7a1eab" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:46:42 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:03 2006 -0800" }, "message": "[PATCH] x86_64: Fix get_cmos_time()\n\nDue to a broken condition, the body of the loop that is intended to wait for\nthe Update-In-Progress bit to get set and then cleared again was never\nentered; in fact, the entire loop was optimized out by the compiler. Here is\na change to fix the condition (and to also move the initialization of locals\nout of the spin lock protected region).\n\nSigned-Off-By: Jan Beulich \u003cjbeulich@novell.com\u003e\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bdf2b1c9fedf76a1797216559f221e5eaa7a1eab", "tree": "bfc206dfdf0754c6475df7bd8cffdcbec69fcd4f", "parents": [ "dd52d642db8ca05267456a07a592922e8b093e1c" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:39 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:02 2006 -0800" }, "message": "[PATCH] x86_64: No need to export get_cmos_time anymore\n\nIt was only needed for APM\n\nPointed out by Jan Beulich\n\nCc: jbeulich@novell.com\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "dd52d642db8ca05267456a07a592922e8b093e1c", "tree": "325cbfbe911c806a8aefb04f5b0c3a5d90d06c94", "parents": [ "2e664aa2bad56b0bb52cf9cb9d14c9b575b437bb" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:36 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:02 2006 -0800" }, "message": "[PATCH] x86_64: Remove unused AMD K8 C stepping flag\n\nX86_FEATURE_K8_C was a synthetic Linux CPUID flag that was used for some\ncode optimizations in Opteron C stepping or later. But support for pre C\nstepping optimizations has been removed, so this isn\u0027t needed anymore.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2e664aa2bad56b0bb52cf9cb9d14c9b575b437bb", "tree": "fc7173b4c61e9adb69e4523680f7d790cf90c351", "parents": [ "77a75333a3d16b830ccf47cf51d944655b015363" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:33 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:02 2006 -0800" }, "message": "[PATCH] i386: Move phys_proc_id/early intel workaround to correct function.\n\nearly_cpu_detect only runs on the BP, but this code needs to run\non all CPUs.\n\nLooks like a mismerge somewhere. Also add a warning comment.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "77a75333a3d16b830ccf47cf51d944655b015363", "tree": "7c911f2763b640a14bfcefd5c3832ccdd93f69e5", "parents": [ "cf0501328674849f8becf6de16620067a0c2f1b5" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@osdl.org", "time": "Wed Jan 11 22:46:30 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:02 2006 -0800" }, "message": "[PATCH] x86_64: sparse warning cleanups\n\nFix some trivial sparse warnings in x86_64 code.\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@osdl.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "cf0501328674849f8becf6de16620067a0c2f1b5", "tree": "6f449d3b82bc178573d8a991e29c1eff8e6b94a5", "parents": [ "cdc4b9c01909d606afbc1e4a4b6c21fa1687a016" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:27 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:01 2006 -0800" }, "message": "[PATCH] x86_64: Move NUMA page_to_pfn/pfn_to_page functions out of line\n\nSaves about ~18K .text in defconfig\n\nThere would be more optimization potential, but that\u0027s for later.\n\nSuggestion originally from Bill Irwin.\nFix from Andy Whitcroft.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "cdc4b9c01909d606afbc1e4a4b6c21fa1687a016", "tree": "4c4c7191509f6527cc3813af1ee92f07bea0bbed", "parents": [ "af5b98042452cc6f50de8afa9d079bda8556d74d" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:46:24 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:01 2006 -0800" }, "message": "[PATCH] x86_64: Remove unused segments\n\nThey used to be used by the reboot code, but not anymore.\n\nNoticed by Jan Beulich\n\nCc: JBeulich@novell.com\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "af5b98042452cc6f50de8afa9d079bda8556d74d", "tree": "bcfbd3e0ed8daae81ddd7098346334aea93e1d94", "parents": [ "79f12614a6537cc3ac9ca4d1ea26f6e4f4a34aee" ], "author": { "name": "Vivek Goyal", "email": "vgoyal@in.ibm.com", "time": "Wed Jan 11 22:46:21 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:01 2006 -0800" }, "message": "[PATCH] x86_64: ioapic virtual wire mode fix\n\no Currently, during kexec reboot, IOAPIC is re-programmed back to virtual\n wire mode if there was an i8259 connected to it. This enables getting\n timer interrupts in second kernel in legacy mode.\n\no After putting into virtual wire mode, IOAPIC delivers the i8259 interrupts\n to CPU0. This works well for kexec but not for kdump as we might crash\n on a different CPU and second kernel will not see timer interrupts.\n\no This patch modifies the redirection table entry to deliver the timer\n interrupts to the cpu we are rebooting (instead of hardcoding to zero).\n This ensures that second kernel receives timer interrupts even on a\n non-boot cpu.\n\nSigned-off-by: Vivek Goyal \u003cvgoyal@in.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "79f12614a6537cc3ac9ca4d1ea26f6e4f4a34aee", "tree": "25167c8862ad7733c7e044b0aad67e4291a0681b", "parents": [ "5fd63b308569060ffa40af52ed122d9734111bff" ], "author": { "name": "Ravikiran G Thirumalai", "email": "kiran@scalex86.org", "time": "Wed Jan 11 22:46:18 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:01 2006 -0800" }, "message": "[PATCH] x86_64: Inclusion of ScaleMP vSMP architecture patches - vsmp_arch\n\nIntroduce vSMP arch to the kernel.\n\nThis patch:\n1. Adds CONFIG_X86_VSMP\n2. Adds machine specific macros for local_irq_disabled, local_irq_enabled\n and irqs_disabled\n3. Writes to the vSMP CTL device to indicate kernel compiled with CONFIG_VSMP\n\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalemp.com\u003e\nSigned-off-by: Shai Fultheim \u003cshai@scalemp.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1008fddcaed7ad3e69f72939c87b24d0d3387ca2", "tree": "916bb6d6d4a6e4ee6e92d936ec9ee322bbd6a7ed", "parents": [ "60923df35edab273d0bd8e829cdfdc5cfbb4fd2c" ], "author": { "name": "Eric W. Biederman", "email": "ebiederm@xmission.com", "time": "Wed Jan 11 22:46:06 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:00 2006 -0800" }, "message": "[PATCH] x86_64: Memorize location of i8259 for reboots.\n\nCurrently we attempt to restore virtual wire mode on reboot, which only\nworks if we can figure out where the i8259 is connected. This is very\nuseful when we are kexec another kernel and likely helpful to an peculiar\nBIOS that make assumptions about how the system is setup.\n\nSince the acpi MADT table does not provide the location where the i8259 is\nconnected we have to look at the hardware to figure it out.\n\nMost systems have the i8259 connected the local apic of the cpu so won\u0027t be\naffected but people running Opteron and some serverworks chipsets should be\nable to use kexec now.\n\nIn addition this patch removes the hard coded assumption that the io_apic\nthat delivers isa interrups is always known to the kernel as io_apic 0.\nThere does not appear to be anything to guarantee that assumption is true.\n\nAnd From: Vivek Goyal \u003cvgoyal@in.ibm.com\u003e\n\n A minor fix to the patch which remembers the location of where i8259 is\n connected. Now counter i has been replaced by apic. counter i is having\n some junk value which was leading to non-detection of i8259 connected to\n IOAPIC.\n\nSigned-off-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nSigned-off-by: Vivek Goyal \u003cvgoyal@in.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "60923df35edab273d0bd8e829cdfdc5cfbb4fd2c", "tree": "d4869124d1344f711671a33628e5eebb16ecd68c", "parents": [ "100c0e36852a771864c56c31b260b7810b554170" ], "author": { "name": "Chuck Ebbert", "email": "76306.1226@compuserve.com", "time": "Wed Jan 11 22:46:03 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:00 2006 -0800" }, "message": "[PATCH] x86_64: allow setting RF in EFLAGS\n\nSetting RF (resume flag) allows a debugger to resume execution after a code\nbreakpoint without tripping the breakpoint again. It is reset by the CPU\nafter executing one instruction.\n\nSigned-off-by: Chuck Ebbert \u003c76306.1226@compuserve.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "100c0e36852a771864c56c31b260b7810b554170", "tree": "e1eb184d7e390b151aab1b13f088849e8bff9ce6", "parents": [ "68209407856507cda9d085470e8d28542ed1a941" ], "author": { "name": "Chuck Ebbert", "email": "76306.1226@compuserve.com", "time": "Wed Jan 11 22:46:00 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:00 2006 -0800" }, "message": "[PATCH] x86_64: \"invalid operand\" -\u003e \"invalid opcode\"\n\nThe manual says Int 6 is \"invalid opcode\", not \"invalid operand\".\n\nSigned-off-by: Chuck Ebbert \u003c76306.1226@compuserve.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "68209407856507cda9d085470e8d28542ed1a941", "tree": "52ec3b64ab5a7a7c1eb169ca369ea4922704adb5", "parents": [ "915f34e20c20ee383832bce0a4bc962d0c86be8d" ], "author": { "name": "Luiz Fernando Capitulino", "email": "lcapitulino@mandriva.com.br", "time": "Wed Jan 11 22:45:57 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:00 2006 -0800" }, "message": "[PATCH] x86_64: Sparse warnings fix.\n\n Fixes the following sparse warnings:\n\narch/x86_64/kernel/mce_amd.c:321:29: warning: Using plain integer as NULL pointer\narch/x86_64/kernel/mce_amd.c:410:41: warning: Using plain integer as NULL pointer\n\nSigned-off-by: Luiz Capitulino \u003clcapitulino@mandriva.com.br\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "915f34e20c20ee383832bce0a4bc962d0c86be8d", "tree": "2e1914cc129361d15e0ad8d888913a0623aef80b", "parents": [ "e080e9d66fd276ed34bc2834eedc134189b87fc9" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:54 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:05:00 2006 -0800" }, "message": "[PATCH] x86_64: Remove useless KDB vector\n\nIt was set as an NMI, but the NMI bit always forces an interrupt\nto end up at vector 2. So it was never used. Remove.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "5b22a3855127bb8221bc96e8e41064b3c5b2bf08", "tree": "3b7af627e49122d567fa2da50b7ef54446237127", "parents": [ "7554c3f0e378161fb6315160d6c3e23bf2de5869" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:48 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:59 2006 -0800" }, "message": "[PATCH] x86_64: Tell user to enable GART_IOMMU when needed\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7554c3f0e378161fb6315160d6c3e23bf2de5869", "tree": "9e7b3679fbf08c11dd2629b6dd1e84931468a746", "parents": [ "365ba9179f84244d2ffa98e46ae3cddfeb2ef6ff" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:45 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:59 2006 -0800" }, "message": "[PATCH] x86_64: Fix warning in nmi.c on uniprocessor kernels\n\nFix\n\n CC arch/x86_64/kernel/nmi.o\nlinux/arch/x86_64/kernel/nmi.c: In function ???check_nmi_watchdog???:\nlinux/arch/x86_64/kernel/nmi.c:155: warning: statement with no effect\n\non Uniprocessor builds.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "365ba9179f84244d2ffa98e46ae3cddfeb2ef6ff", "tree": "b84be7f9f929d8084fa76af2618877439baee841", "parents": [ "df79efde82952edc653fa6eb1338a82b87aa0585" ], "author": { "name": "Ravikiran G Thirumalai", "email": "kiran@scalex86.org", "time": "Wed Jan 11 22:45:42 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:59 2006 -0800" }, "message": "[PATCH] x86_64: Allocate PDAs in the local node\n\nPatch uses a static PDA array early at boot and reallocates processor PDA\nwith node local memory when kmalloc is ready, just before pda_init.\nThe boot_cpu_pda is needed since the cpu_pda is used even before pda_init for\nthat cpu is called (to set the static per-cpu areas offset table etc)\n\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nSigned-off-by: Shai Fultheim \u003cshai@scalex86.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "df79efde82952edc653fa6eb1338a82b87aa0585", "tree": "67abb221cf834c3a7766c406aae1e55aa31b6bcf", "parents": [ "05b3cbd8bb98736387df8a2e1efe311b1fb4d2ad" ], "author": { "name": "Ravikiran G Thirumalai", "email": "kiran@scalex86.org", "time": "Wed Jan 11 22:45:39 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:59 2006 -0800" }, "message": "[PATCH] x86_64: Node local pda take 2 -- cpu_pda preparation\n\nHelper patch to change cpu_pda users to use macros to access cpu_pda\ninstead of the cpu_pda[] array.\n\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nSigned-off-by: Shai Fultheim \u003cshai@scalex86.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "05b3cbd8bb98736387df8a2e1efe311b1fb4d2ad", "tree": "46ca01cfe38d2df4c6f93ba0325a3f2a1e97ea71", "parents": [ "0b91317e338f42367de6d53f5e14f273aae7d034" ], "author": { "name": "Ravikiran Thirumalai", "email": "kiran@scalex86.org", "time": "Wed Jan 11 22:45:36 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:59 2006 -0800" }, "message": "[PATCH] x86_64: Early initialization of cpu_to_node\n\nPatch enables early intialization of cpu_to_node.\napicid_to_node is built by reading the SRAT table, from acpi_numa_init with\nACPI_NUMA and k8_scan_nodes with K8_NUMA.\nx86_cpu_to_apicid is built by parsing the ACPI MADT table, from acpi_boot_init.\nWe combine these two tables and setup cpu_to_node.\n\nEarly intialization helps the static per_cpu_areas in getting pages from\ncorrect node.\n\nChange since last release:\nDo not initialize early init_cpu_to_node for faking node cases.\n\nPatch tested on TYAN dual core 4P board with K8 only, ACPI_NUMA.\nTested on EM64T NUMA. Also tested with numa\u003doff, numa\u003dfake, and running\na kernel compiled with NUMA on a regular EM64 2 way SMP.\n\nSigned-off-by: Alok N Kataria \u003calokk@calsoftinc.com\u003e\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nSigned-off-by: Shai Fultheim \u003cshai@scalex86.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "0b91317e338f42367de6d53f5e14f273aae7d034", "tree": "24bfddda3589fc01af2d5d70f39791860cc74b13", "parents": [ "2c8bc9446a853f4f36475ce314808dd92201f74e" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:33 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:58 2006 -0800" }, "message": "[PATCH] x86_64: Fix up white space in time.c\n\nNo functional changes.\n\nAnd remove one redundant prototype.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2c8bc9446a853f4f36475ce314808dd92201f74e", "tree": "9f69acf8a0d5fabd85f753ecff8bbd77b3aacdc4", "parents": [ "487472bc01fab0625996aad37836aad931e4eda9" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:30 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:58 2006 -0800" }, "message": "[PATCH] x86_64: Use standard __always_inline in vsyscall.c\n\nReplacing the old home brewn __force_inline.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "487472bc01fab0625996aad37836aad931e4eda9", "tree": "ede143ee4c756413b396911b3702068283b052f2", "parents": [ "c818a18146997d1356a4840b0c01f1168c16c8a4" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:27 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:58 2006 -0800" }, "message": "[PATCH] i386: Replace broken serialize_cpu in microcode driver with correct sync_core\n\nPassing random input values in eax to cpuid is not a good idea\nbecause the CPU will GPF for unknown ones.\nUse the correct x86-64 version that exists for a longer time too.\nThis also adds a memory barrier to prevent the optimizer from\nreordering.\n\nCc: tigran@veritas.com\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c818a18146997d1356a4840b0c01f1168c16c8a4", "tree": "8d7e049742e87666bf3089fe46e04828b6417fd7", "parents": [ "7f6c5b046978d68e69bdc73433ead41612a2a1c9" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:24 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:58 2006 -0800" }, "message": "[PATCH] x86_64: On Intel CPUs don\u0027t do an additional CPU sync before RDTSC\n\nRDTSC serialization using cpuid is not needed for Intel platforms.\nThis increases gettimeofday performance.\n\nCc: vojtech@suse.cz\nCc: rohit.seth@intel.com\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7f6c5b046978d68e69bdc73433ead41612a2a1c9", "tree": "60f74adc6166496fbd84143272ad3b88254f9b72", "parents": [ "6e54d95f73bbc79171802a1983e0c3835676db88" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:21 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:58 2006 -0800" }, "message": "[PATCH] x86_64: Support alternative() in vsyscalls\n\nThe real vsyscall .text addresses are not mapped when the alternative()\nreplacement runs early, so use some black magic to access them using\nthe direct mapping.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "737c5c3bde5641af9c24e3a60366674af72a43ef", "tree": "e369c6489279c9fda4a5fb1766fe1966ce9caf87", "parents": [ "3c0217511313a46039137d2dab30fdb1c5a65e64" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:45:15 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:57 2006 -0800" }, "message": "[PATCH] x86_64: Don\u0027t try to synchronize the TSC over CPUs on Intel CPUs at boot.\n\nThey already do this in hardware and the Linux algorithm\nactually adds errors.\n\nCc: mingo@elte.hu\nCc: rohit.seth@intel.com\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b9d1e4bd6e44f2a75340226eb5f762e16bb4652f", "tree": "e886056fb4a412e98e8f52e559c16be95994db55", "parents": [ "aea9fca1dc8a1f9ac5d3b76ef04516a010cbf2e4" ], "author": { "name": "Vivek Goyal", "email": "vgoyal@in.ibm.com", "time": "Wed Jan 11 22:45:09 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:57 2006 -0800" }, "message": "[PATCH] x86_64: x86_64 write apic id fix\n\no Apic id is in most significant 8 bits of APIC_ID register. Current code\n is trying to write apic id to least significant 8 bits. This patch fixes\n it.\n\no This fix enables booting uni kdump capture kernel on a cpu with non-zero\n apic id.\n\nSigned-off-by: Vivek Goyal \u003cvgoyal@in.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "aea9fca1dc8a1f9ac5d3b76ef04516a010cbf2e4", "tree": "7258695b655ce600c84c67269489a8093ae92c81", "parents": [ "e3602824cb1172deeb0f2b286025753882b90b28" ], "author": { "name": "Brian Gerst", "email": "bgerst@didntduck.org", "time": "Wed Jan 11 22:45:06 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:56 2006 -0800" }, "message": "[PATCH] x86_64: Remove duplicate exports\n\nRemove exports that are already exported from the object\u0027s source file.\n\nSigned-off-by: Brian Gerst \u003cbgerst@didntduck.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e3602824cb1172deeb0f2b286025753882b90b28", "tree": "8f2cb7feee5b780bd7358c05844df0bfb9353e37", "parents": [ "2d0db401ee4ee08857b79f1d3be40e8a819f8992" ], "author": { "name": "Brian Gerst", "email": "bgerst@didntduck.org", "time": "Wed Jan 11 22:45:03 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:56 2006 -0800" }, "message": "[PATCH] x86_64: unexport pci_*_consistent\n\nThese functions are inlines and shouldn\u0027t be exported.\n\nSigned-off-by: Brian Gerst \u003cbgerst@didntduck.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4855170f9876c8b4a16f115f32cf6851bac1ffcc", "tree": "163b0c5118421c290f52ec4ae638084b9224fa02", "parents": [ "2cbc9ee35c992f88fb2558a4f13920e3df4ef3bb" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:48 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:55 2006 -0800" }, "message": "[PATCH] x86_64: Make it clear in machine checks that it\u0027s an hardware problem\n\nHopefully the users will take the hint.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2cbc9ee35c992f88fb2558a4f13920e3df4ef3bb", "tree": "51bed27fe9050cae3e7de2d24f55874455316ab2", "parents": [ "17a941d854a3f7b0bb916fdeee4c9ffdcc19d8d3" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:45 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:55 2006 -0800" }, "message": "[PATCH] x86_64: Clean up copy_*_user\n\n- Remove optimization for old B stepping Opteron\n- Make the fast path for copies with a multiple of eight length faster.\n- Minor instruction rearrangement to hopefully avoid a pipeline\nstall or two.\n- Add comment about errata to consider.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "17a941d854a3f7b0bb916fdeee4c9ffdcc19d8d3", "tree": "b6b3b55318336adf769bf57141a01a9defbbb202", "parents": [ "8a6fdd3e912e0ce6f723431d66baf704bf8a1d26" ], "author": { "name": "Muli Ben-Yehuda", "email": "mulix@mulix.org", "time": "Wed Jan 11 22:44:42 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:55 2006 -0800" }, "message": "[PATCH] x86_64: Use function pointers to call DMA mapping functions\n\nAK: I hacked Muli\u0027s original patch a lot and there were a lot\nof changes - all bugs are probably to blame on me now.\nThere were also some changes in the fall back behaviour\nfor swiotlb - in particular it doesn\u0027t try to use GFP_DMA\nnow anymore. Also all DMA mapping operations use the\nsame core dma_alloc_coherent code with proper fallbacks now.\nAnd various other changes and cleanups.\n\nKnown problems: iommu\u003dforce swiotlb\u003dforce together breaks\n needs more testing.\n\nThis patch cleans up x86_64\u0027s DMA mapping dispatching code. Right now\nwe have three possible IOMMU types: AGP GART, swiotlb and nommu, and\nin the future we will also have Xen\u0027s x86_64 swiotlb and other HW\nIOMMUs for x86_64. In order to support all of them cleanly, this\npatch:\n\n- introduces a struct dma_mapping_ops with function pointers for each\n of the DMA mapping operations of gart (AMD HW IOMMU), swiotlb\n (software IOMMU) and nommu (no IOMMU).\n\n- gets rid of:\n\n if (swiotlb)\n return swiotlb_xxx();\n\n- PCI_DMA_BUS_IS_PHYS is now checked against the dma_ops being set\nThis makes swiotlb faster by avoiding double copying in some cases.\n\nSigned-Off-By: Muli Ben-Yehuda \u003cmulix@mulix.org\u003e\nSigned-Off-By: Jon D. Mason \u003cjdmason@us.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8a6fdd3e912e0ce6f723431d66baf704bf8a1d26", "tree": "930056ca5dc50ce6245cd602f044e224dd5a8776", "parents": [ "95833c83f3b812c78e48db4eaa19f6c74958470b" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:39 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:55 2006 -0800" }, "message": "[PATCH] x86_64: Reject SRAT tables that don\u0027t cover all memory\n\nBroken BIOS on Iwill 8way systems reports these and it causes the bootmem\nallocator to crash. Add a sanity check if all the PXMs in the\nSRAT table cover all memory as reported by e820. If the sanity\ncheck fails the SRAT is rejected and the code will fall back\nto discover the NUMA topology using the K8 northbridge registers\nwhen applicable.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "95833c83f3b812c78e48db4eaa19f6c74958470b", "tree": "8ad17da708141d66cf53c2113b4fe1710af929ec", "parents": [ "6b050f8075823b0d9ec4fad38f4f552b74e5c5af" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:36 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:55 2006 -0800" }, "message": "[PATCH] x86_64: Add idle notifiers\n\nThis adds a new notifier chain that is called with IDLE_START\nwhen a CPU goes idle and IDLE_END when it goes out of idle.\nThe context can be idle thread or interrupt context.\n\nSince we cannot rely on MONITOR/MWAIT existing the idle\nend check currently has to be done in all interrupt\nhandlers.\n\nThey were originally inspired by the similar s390 implementation.\n\nThey have a variety of applications:\n- They will be needed for CONFIG_NO_IDLE_HZ\n- They can be used for oprofile to fix up the missing time\nin idle when performance counters don\u0027t tick.\n- They can be used for better C state management in ACPI\n- They could be used for microstate accounting.\n\nThis is just infrastructure so far, no users.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6b050f8075823b0d9ec4fad38f4f552b74e5c5af", "tree": "f2e6f95f7140b06ee8dae4bb03d4d4e78df69e54", "parents": [ "d18ff47068154de8b4c1506be60a30a961846d18" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:33 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:55 2006 -0800" }, "message": "[PATCH] x86_64: Clean up some printks in NUMA code\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "d18ff47068154de8b4c1506be60a30a961846d18", "tree": "bce5eb01243c89b0e07fd3f02de251ac2645ec2a", "parents": [ "ca8642f606ce22de23bae08a5044067f98de855b" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:30 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:54 2006 -0800" }, "message": "[PATCH] x86_64: Fix up coding style in numa.c\n\nNo functional changes\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ca8642f606ce22de23bae08a5044067f98de855b", "tree": "143dd169cbba9d58629ca74d618cbfa41964c2f8", "parents": [ "d25bf7e5fe73b5b6d2246ab0be08ae35d718456b" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:27 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:54 2006 -0800" }, "message": "[PATCH] x86_64: Fix off by one in IOMMU check\n\nFix off by one when checking if the machine has enougn memory to need IOMMU\nThis caused the IOMMUs to be needlessly enabled for mem\u003d4G\n\nBased on a patch from Jon Mason\n\nSigned-off-by: jdmason@us.ibm.com\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "d25bf7e5fe73b5b6d2246ab0be08ae35d718456b", "tree": "472749fef9b017e9a4d94f9e07a29dc44c3294cb", "parents": [ "6eb0a0fd059598ee0d49c6283ce25cccd743e9fc" ], "author": { "name": "Venkatesh Pallipadi", "email": "venkatesh.pallipadi@intel.com", "time": "Wed Jan 11 22:44:24 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:54 2006 -0800" }, "message": "[PATCH] x86_64: Handle missing local APIC timer interrupts on C3 state\n\nWhenever we see that a CPU is capable of C3 (during ACPI cstate init), we\ndisable local APIC timer and switch to using a broadcast from external timer\ninterrupt (IRQ 0).\n\nPatch below adds the code for x86_64.\n\nSigned-off-by: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6eb0a0fd059598ee0d49c6283ce25cccd743e9fc", "tree": "a608f92e3b8a94cba89e94786169897c64629580", "parents": [ "5a07a30c3cc4dc438494d6416ffa74008a2194b3" ], "author": { "name": "Venkatesh Pallipadi", "email": "venkatesh.pallipadi@intel.com", "time": "Wed Jan 11 22:44:21 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:54 2006 -0800" }, "message": "[PATCH] i386: Handle missing local APIC timer interrupts on C3 state\n\nWhenever we see that a CPU is capable of C3 (during ACPI cstate init), we\ndisable local APIC timer and switch to using a broadcast from external timer\ninterrupt (IRQ 0). This is needed because Intel CPUs stop the local\nAPIC timer in C3. This is currently only enabled for Intel CPUs.\n\nPatch below adds the code for i386 and also the ACPI hunk.\n\nSigned-off-by: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "5a07a30c3cc4dc438494d6416ffa74008a2194b3", "tree": "eafda8ee2f58f392f5d78af7748ce58ddb6bf9a2", "parents": [ "01b8faaef5d239aeabb1e712c5d9619f29e808dd" ], "author": { "name": "Venkatesh Pallipadi", "email": "venkatesh.pallipadi@intel.com", "time": "Wed Jan 11 22:44:18 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:54 2006 -0800" }, "message": "[PATCH] i386/x86-64: Remove sub jiffy profile timer support\n\nRemove the finer control of local APIC timer. We cannot provide a sub-jiffy\ncontrol like this when we use broadcast from external timer in place of\nlocal APIC. Instead of removing this only on systems that may end up using\nbroadcast from external timer (due to C3), I am going the\n\"I\u0027m feeling lucky\" way to remove this fully. Basically, I am not sure about\nusefulness of this code today. Few other architectures also don\u0027t seem to\nsupport this today.\n\nIf you are using profiling and fine grained control and don\u0027t like this going\naway in normal case, yell at me right now.\n\nSigned-off-by: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "01b8faaef5d239aeabb1e712c5d9619f29e808dd", "tree": "5f04e7d96c14d4d6c7280abcb2048907079ccbb9", "parents": [ "4839057cafc9a508ad5906857e9c1d8707c875e3" ], "author": { "name": "John Blackwood", "email": "john.blackwood@ccur.com", "time": "Wed Jan 11 22:44:15 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:54 2006 -0800" }, "message": "[PATCH] x86_64: Report hardware breakpoints in user space when triggered by the kernel\n\nI would like to throw out a suggestion for a possible change in the way that\nthe debug register traps are handled in do_debug() when the trap occurs\nin kernel-mode.\n\nIn the x86_64 version of do_debug(), the code will skip around sending\na SIGTRAP to the current task if the trap occurred while in kernel mode.\n\nOn the i386-side of things, if the access happens to occur in kernel mode\n(say during a read(2) of user\u0027s buffer that matches the address of a\ndebug register trap), then the do_debug() routine for i386 will go ahead\nand call send_sigtrap() and send the SIGTRAP signal. The send_sigtrap()\ncode will also set the info.si_addr to NULL in this case (even though I\ndon\u0027t understand why, since the SIGTRAP siginfo processing doesn\u0027t use\nthe si_addr field...).\n\nSo I would like to suggest that the x86_64 do_debug() routine also\nfollow this type of behavior and have it go ahead and send the\nSIGTRAP signal to the current task, even if the debug register trap\nhappens to have occurred in kernel mode. I have taken a stab at\na patch for this change below. (It includes the i386-ish change\nfor setting si_addr to NULL when the trap occurred in kernel mode.)\n\nIt seems like a useful feature to be able to \u0027watch\u0027 a user location that\nmight also be modified in the kernel via a system service call, and have the\ndebugger report that information back to the user, rather than to just\nsilently ignore the trap.\n\nAdditionally, I realize that users that pull in a kernel debugger such as\nKGDB into their kernel might want to remove this change below when they add\nin KGDB support. However, they could alternatively look at the current\ntask\u0027s thread.debugreg[] values to see if the trap occurred due to KGDB\nor instead because of a user-space debugger trap, and still honor the\nuser SIGTRAP processing (instead of the KGDB breakpoint processing)\nif the trap matches up with the thread.debugreg[] registers.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "66c581569e2cb41231b3fcd91a6c9f853d4d4e25", "tree": "b7e4629b9eeee9850e2ba4be32c2ee3c0afb6959", "parents": [ "bf2fcc6fdfe4f4e92bb74f062c0a1be189f3a561" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:09 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:53 2006 -0800" }, "message": "[PATCH] x86_64: Convert page fault error codes to symbolic constants.\n\nMuch better to deal with these than with the magic numbers.\n\nAnd remove the comment describing the bits - kernel source\nis no replacement for an architecture manual.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bf2fcc6fdfe4f4e92bb74f062c0a1be189f3a561", "tree": "0bcc33f681c7e8ce6596c9323d4a1026ede84994", "parents": [ "2966387b481a11a90a7bed6600fc17b4253f6980" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:06 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:53 2006 -0800" }, "message": "[PATCH] x86_64: Implement is_compat_task the right way\n\nBy setting a flag during a 32bit system call only\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f95190b28daa1bebf78ab5ec4129d01a223982c5", "tree": "d6a022685daf4c27a3583f25937f35d20051ebf7", "parents": [ "c11efdf94d3152443c11334720824bb6c7f6c655" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:44:00 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:53 2006 -0800" }, "message": "[PATCH] x86_64: Remove unnecessary case from the page fault handler\n\nDon\u0027t need to do the vmalloc check for the module range because its\nPML4 is shared with the kernel text.\n\nAlso removed an unnecessary TLB flush.\n\nPointed out by Jan Beulich\n\nCc: jbeulich@novell.com\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c11efdf94d3152443c11334720824bb6c7f6c655", "tree": "d4185d8de8b855aca51b6bec730aeab3342e2a0f", "parents": [ "bb33421dde79f9a36d5485c56335ff178ac7d268" ], "author": { "name": "Ravikiran G Thirumalai", "email": "kiran@scalex86.org", "time": "Wed Jan 11 22:43:57 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:53 2006 -0800" }, "message": "[PATCH] x86_64: Align and pad x86_64 GDT on page boundary\n\nThis patch is on the same lines as Zachary Amsden\u0027s i386 GDT page alignemnt\npatch in -mm, but for x86_64.\n\nPatch to align and pad x86_64 GDT on page boundries.\n\n[AK: some minor cleanups and fixed incorrect TLS initialization\nin CPU init.]\n\nSigned-off-by: Nippun Goel \u003cnippung@calsoftinc.com\u003e\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nSigned-off-by: Shai Fultheim \u003cshai@scalex86.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bb33421dde79f9a36d5485c56335ff178ac7d268", "tree": "f4b8843d9295c1efb550e869352e578cb8667ce1", "parents": [ "79c62cf1789f935280138b412bb750be84aec747" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:43:54 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:52 2006 -0800" }, "message": "[PATCH] x86_64: Allow compilation on a 32bit biarch toolchain\n\nThis might help on distributions that use a 32bit biarch compiler.\n\nFirst pass -m64 by default.\n\nSecondly add some more .code32s because at least the Ubuntu biarch\n32bit as called by gcc doesn\u0027t seem to handle -m64 -m32 as generated\nby the Makefile without such assistance.\n\nAnd finally make sure the linker script can be preprocessed\nwith a 32bit cpp.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "79c62cf1789f935280138b412bb750be84aec747", "tree": "24c522ed0dd3dba942f1db43048205b0973aa7c8", "parents": [ "e4e94072d9c3b19662537cbd5e2d37bcaeed3d9b" ], "author": { "name": "Ross Biro", "email": "ross.biro@gmail.com", "time": "Wed Jan 11 22:43:51 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:52 2006 -0800" }, "message": "[PATCH] x86_64: Make udelay more accurate\n\nThe attempt to avoid overflow in __delay caused varying precision\non different CPUs depending on differences in the CPU speed.\n\nWe should be able to do this multiplication with out overflowing\nprovided the\ncpu is running at less than about 128 GHz. xloops \u003c 20000 * 0x10c6.\nloops_per_jiffy * HZ \u003c\u003d cpu_clock_speed. So if the cpu clock speed\n\u003c 2^64/(20000 * 0x10c6) \u003d 2^64/ 51E6CC0 \u003c 2^64/2^27 \u003d 2^37 \u003d 128G we\nwill not overflow the calculation.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e4e94072d9c3b19662537cbd5e2d37bcaeed3d9b", "tree": "1d2c1c61319ea999703090023551204606525a1d", "parents": [ "819a692804a8d2d42b7bb033d2650dba47622149" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:43:48 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:52 2006 -0800" }, "message": "[PATCH] x86_64: Return -1 for unknown PCI bus affinity\n\nWhen we don\u0027t know the node a PCI bus is connected to return -1.\nThis matches the generic code.\n\nNoticed by Ravikiran G Thirumalai \u003ckiran@scalex86.org\u003e\n\nCc: Ravikiran G Thirumalai \u003ckiran@scalex86.org\u003e\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1584b89c921acefe88881f08d836d80f00600a84", "tree": "112d64a284488f490045b19aa910bb1b2abcbff4", "parents": [ "7a4a76cc1057de0dc96ee481590347aa8c5b9ffb" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:43:42 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:51 2006 -0800" }, "message": "[PATCH] x86_64: Validate SLIT table\n\nA lot of Opteron BIOS just pass 10 in all SLIT entries (10 is the\nnormalized unit). This is actually worse than the default heuristic\nbecause it leads to pci_distance not knowing the difference between\nlocal and remote nodes anymore. This messes up some NUMA\nheuristics in generic code.\n\nIn this case it\u0027s better to fall back to the default heuristic\nwhich just does nodea \u003d\u003d nodeb ? 10 : 20.\n\nThis patch does some basic sanity checking on the SLIT and only accepts\nthe SLIT when it passes.\n\nInvariants enforced are:\n- Node to itself shall be 10\n- Any other distance shouldn\u0027t be 10\n- Distances smaller than 10 are illegal\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7a4a76cc1057de0dc96ee481590347aa8c5b9ffb", "tree": "b2f2b8d46fc859b2ec4e7b6e1d3d24ffc7d1c507", "parents": [ "7180d4fb83085fef9d24b353f5bd79cf6fd98447" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:43:39 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:51 2006 -0800" }, "message": "[PATCH] x86_64: Fix off by one in acpi table mapping\n\nAnd fix the test to include the size\n\nNoticed by Vivek Goyal\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e99286744599a66195de4cd975d7ef4d643c2789", "tree": "d231b075c9bdb0bd7fa48d0eb00551a529e4586a", "parents": [ "b347d25fbc4616f4f37895e9afbe25b2bbc7e11f" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:43:33 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:51 2006 -0800" }, "message": "[PATCH] x86_64: Generalize DMI and enable for x86-64\n\nSome people need it now on 64bit so reuse the i386 code for\nx86-64. This will be also useful for future bug workarounds.\n\nIt is a bit simplified there because there is no need\nto do it very early on x86-64. This means it doesn\u0027t need\nearly ioremap et.al. We run it as a core initcall right now.\n\nI hope it\u0027s not needed for early setup.\n\nI added a general CONFIG_DMI symbol in case IA64 or someone\nelse wants to reuse the code later too.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b347d25fbc4616f4f37895e9afbe25b2bbc7e11f", "tree": "dff624ba5f0e15a3c5abf4a9679f15be1f50abf0", "parents": [ "f46ace69282e9791757ec7d7b130285124ec10d0" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:43:30 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:51 2006 -0800" }, "message": "[PATCH] x86_64: Remove bogus file in arch/x86_64/pci\n\nThis was a backup file that somehow made it into the official\ntree. Never used for anything. Remove.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f46ace69282e9791757ec7d7b130285124ec10d0", "tree": "37d3e0cfa44e19182d99e5574a0d21baa1a5fa8a", "parents": [ "636dd2b7def5c9c72551b51d4d516a65c269de08" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:43:27 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:51 2006 -0800" }, "message": "[PATCH] x86_64: Add missing newline in IOMMU error message\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bd9cb64df1d99c07ea9672661ede6ca3ba5c6579", "tree": "6f9e9e81aad3f554b5ca1e8cae1ad7c3b9676bbf", "parents": [ "4724e3e86d806860c90917f9b73d4354e388b39b" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:43:21 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:50 2006 -0800" }, "message": "[PATCH] x86_64: fix page fault from show_trace()\n\nThe introduction of call_softirq switching to the interrupt stack several\nreleases earlier resulted in a problem with the code in show_trace, which\nassumes that it can pick the previous stack pointer from the end of the\ninterrupt stack.\n\nCc: Andi Kleen \u003cak@muc.de\u003e\nCc: Arjan van de Ven \u003carjanv@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4724e3e86d806860c90917f9b73d4354e388b39b", "tree": "f14fb69d8fe50894107c48898f8583fdda985055", "parents": [ "60917a3832547886549962ab9ee753253cf5e44c" ], "author": { "name": "Peter Beutner", "email": "p.beutner@gmx.net", "time": "Wed Jan 11 22:43:18 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:50 2006 -0800" }, "message": "[PATCH] x86_64: fix single step handling for 32bit processes\n\nBe more careful with TF handling to fix some copy protection codes in wine\n\npatch originally for i386 by Linus, then ported to x86_64 by Andi Kleen\nsee: [PATCH] x86_64: Some fixes for single step handling\ncommit: be61bff789fe44bfb6d9282d8f7eccc860bdcfb6\n\nBut it was never applied to the ia32 emulation code which breaks some\ncopy-protection schemes under wine when running on x86_64.\n\nSigned-off-by: Peter Beutner \u003cp.beutner@gmx.net\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6e3fbee5f11a8135109b08bfcbc05a29eb4eabe8", "tree": "2a37bbf126d3312ae2a6a0285ea8c2620f58cc39", "parents": [ "329d400f47ddfe8ff599823d739c5c5565da3207" ], "author": { "name": "Eric W. Biederman", "email": "ebiederm@xmission.com", "time": "Wed Jan 11 22:43:12 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:50 2006 -0800" }, "message": "[PATCH] i386/x86-64: Don\u0027t IPI to offline cpus on shutdown\n\nSo why are we calling smp_send_stop from machine_halt?\n\nWe don\u0027t.\n\nLooking more closely at the bug report the problem here\nis that halt -p is called which triggers not a halt but\nan attempt to power off.\n\nmachine_power_off calls machine_shutdown which calls smp_send_stop.\n\nIf pm_power_off is set we should never make it out machine_power_off\nto the call of do_exit. So pm_power_off must not be set in this case.\nWhen pm_power_off is not set we expect machine_power_off to devolve\ninto machine_halt.\n\nSo how do we fix this?\n\nPlaying too much with smp_send_stop is dangerous because it\nmust also be safe to be called from panic.\n\nIt looks like the obviously correct fix is to only call\nmachine_shutdown when pm_power_off is defined. Doing\nthat will make Andi\u0027s assumption about not scheduling\ntrue and generally simplify what must be supported.\n\nThis turns machine_power_off into a noop like machine_halt\nwhen pm_power_off is not defined.\n\nIf the expected behavior is that sys_reboot(LINUX_REBOOT_CMD_POWER_OFF)\nbecomes sys_reboot(LINUX_REBOOT_CMD_HALT) if pm_power_off is NULL\nthis is not quite a comprehensive fix as we pass a different parameter\nto the reboot notifier and we set system_state to a different value\nbefore calling device_shutdown().\n\nUnfortunately any fix more comprehensive I can think of is not\nobviously correct. The core problem is that there is no architecture\nindependent way to detect if machine_power will become a noop, without\ncalling it.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "329d400f47ddfe8ff599823d739c5c5565da3207", "tree": "903b45e7ebcccbbd8172e207315c036ceb70f6e8", "parents": [ "73ca5358aab55e2e29993a31f3776c54c05ae729" ], "author": { "name": "Zwane Mwaikambo", "email": "zwane@arm.linux.org.uk", "time": "Wed Jan 11 22:43:09 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:57 2006 -0800" }, "message": "[PATCH] x86_64/i386: Remove preempt disable calls in lowlevel IPI\n\nI noticed that some lowlevel send_IPI_mask helpers had a hotplug/preempt\nrace whereupon the cpu_online_map was read before disabling preemption;\n\n...\ncpumask_t mask \u003d cpu_online_map;\nint cpu \u003d get_cpu();\ncpu_clear(cpu, mask);\n...\n\nBut then i realised that there is no need for these lowlevel functions to\nbe going through all this trouble when all the callers are already made\nhotplug/preempt safe.\n\nSigned-off-by: Zwane Mwaikambo \u003czwane@arm.linux.org.uk\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "73ca5358aab55e2e29993a31f3776c54c05ae729", "tree": "8c9c177c9f5a0e1f16e3f01f9aa668f353cfc95e", "parents": [ "f2ecfab91c6f248cf71dff66c2111d31c8cc1747" ], "author": { "name": "Shaohua Li", "email": "shaohua.li@intel.com", "time": "Wed Jan 11 22:43:06 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:57 2006 -0800" }, "message": "[PATCH] x86_64: increase MCE bank counts\n\nThere is one CPU here whose MCE bank count is 6. This patch increases\nx86_64\u0027s MCE bank count.\n\nSigned-off-by: Shaohua Li \u003cshaohua.li@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f2ecfab91c6f248cf71dff66c2111d31c8cc1747", "tree": "4d0c1834fac10d50cb25d53b82d33794df9a625b", "parents": [ "b556b35e98ad2b9174a7a623d152cdf412d1a999" ], "author": { "name": "Benjamin LaHaise", "email": "bcrl@kvack.org", "time": "Wed Jan 11 22:43:03 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:56 2006 -0800" }, "message": "[PATCH] x86_64: another mb() for smpboot.c\n\nThe following is probably a good idea given that the atomic_set() isn\u0027t\na barrier here either.\n\nSigned-off-by: Benjamin LaHaise \u003cbenjamin.c.lahaise@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b556b35e98ad2b9174a7a623d152cdf412d1a999", "tree": "10f99d70e719fba811dee85d2f3a82b26d7a4ce8", "parents": [ "ed8388a5d9db0445322f86ee8381b0f04a2057ee" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:43:00 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:13 2006 -0800" }, "message": "[PATCH] x86_64: Move int 3 handler to debug stack and allow to increase it.\n\nThis\n- switches the INT3 handler to run on an IST stack (to cope with\n breakpoints set by a kernel debugger on places where the kernel\u0027s\n %gs base hasn\u0027t been set up, yet); the IST stack used is shared with\n the INT1 handler\u0027s\n[AK: this also allows setting a kprobe on the interrupt/exception entry\npoints]\n- allows nesting of INT1/INT3 handlers so that one can, with a kernel\n debugger, debug (at least) the user-mode portions of the INT1/INT3\n handling; the nesting isn\u0027t actively enabled here since a kernel-\n debugger-free kernel doesn\u0027t need it\n\nSigned-Off-By: Jan Beulich \u003cjbeulich@novell.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ed8388a5d9db0445322f86ee8381b0f04a2057ee", "tree": "eba3d011ef4973ff7568274215f43f0508e848e5", "parents": [ "7c0ac555b0b927ee0b3ca6200617f43dbdbaffb8" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:57 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:13 2006 -0800" }, "message": "[PATCH] x86_64: Don\u0027t confuse apic\u003d... command line option with apic\n\nPreviously apic was foced with apic\u003dlogopt was specified.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7c0ac555b0b927ee0b3ca6200617f43dbdbaffb8", "tree": "09e24fdaee0975f0725f9b6278c23c8db36b510c", "parents": [ "3f98bc4991df8e7b5972489b4632e1e5c03cd1ee" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:54 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:12 2006 -0800" }, "message": "[PATCH] x86_64: Dont\u0027t disable early PCI scan with apic\n\nIt might be still needed for non APIC related issues.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3f98bc4991df8e7b5972489b4632e1e5c03cd1ee", "tree": "877fc1305c6d2713a891fc52cc5babbe5c0d62dc", "parents": [ "152bf8c55d657898c40c8ed270630c0cf9d51f7d" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:51 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:12 2006 -0800" }, "message": "[PATCH] i386/x86-64: Update AMD CPUID flags\n\nPrint bits for RDTSCP, SVM, CR8-LEGACY.\n\nAlso now print power flags on i386 like x86-64 always did.\nThis will add a new line in the 386 cpuinfo, but that shouldn\u0027t\nbe an issue - did that in the past too and I haven\u0027t heard\nof any breakage.\n\nI shrunk some of the fields in the i386 cpuinfo_x86 to chars\nto make up for the new int \"x86_power\" field. Overall it\u0027s\nsmaller than before.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "152bf8c55d657898c40c8ed270630c0cf9d51f7d", "tree": "952dafe52a4dbe7f61cb01507fbeddc3d1925106", "parents": [ "39b3a7910556005a7a0d042ecb7ff98bfa84ea57" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:48 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:12 2006 -0800" }, "message": "[PATCH] x86_64: Use X86_FEATURE_CONSTANT_TSC now to clean up Intel speedstep drivers\n\nThey previously tried to figure this out on their own.\n\nSuggested by Venkatesh.\n\nCc: venkatesh.pallipadi@intel.com\nCc: davej@redhat.com\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "39b3a7910556005a7a0d042ecb7ff98bfa84ea57", "tree": "efcb2602e6fd198c9af34e726741eb389fa4e292", "parents": [ "2d52ede9876ba566b583f255fdc43800eea81baa" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:45 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:12 2006 -0800" }, "message": "[PATCH] i386/x86-64: Generalize X86_FEATURE_CONSTANT_TSC flag\n\nDefine it for i386 too.\n\nThis is a synthetic flag that signifies that the CPU\u0027s TSC runs\nat a constant P state invariant frequency.\n\nFix up the logic on x86-64/i386 to set it on all known CPUs.\nUse the AMD defined bit to set it on future AMD CPUs.\n\nCc: venkatesh.pallipadi@intel.com\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "2d52ede9876ba566b583f255fdc43800eea81baa", "tree": "07f405b7807ac54a9e091ea6054281d2c290e6c6", "parents": [ "7eb903f4a5c35c8310f0aa7b0e94aae0b826d837" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:42 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:12 2006 -0800" }, "message": "[PATCH] x86_64: Remove enable/disable_hlt\n\nWas only used by the floppy driver to work around some ancient\nhardware bug that should never occur on any 64bit system.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f62a91f6911479642c0018290d4248ace4287648", "tree": "f5d941d1f1dab0bf462795c47fa8b616d31a833f", "parents": [ "92934bcbf96bc9dc931c40ca5f1a57685b7b813b" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:35 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:11 2006 -0800" }, "message": "[PATCH] x86_64: Don\u0027t reserve hotplug CPUs by default\n\nMost users don\u0027t need it so no need to waste memory.\nThis means an user has to specify the appropiate number of\nhotplug CPUs on the command line with additional_cpus\u003d...\nor fix their BIOS to follow the convention in\nDocumentation/x86-64/cpu-hotplug-spec\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "636aab5ce332d88a76362797a55804c7da643467", "tree": "6127968732ba695e30d72f3dfd53252c18ec89ec", "parents": [ "1f6818b90dbb887261c616a318733703ed526f0a" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jan 11 22:42:29 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:11 2006 -0800" }, "message": "[PATCH] x86_64: No need to remove NT during CPU setup\n\nhead.S already clears EFLAGS completely. Following an i386 patch from\nZachary Amsden.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8b1bde93175182d7c11d9a1230b2210a5815e747", "tree": "1394674c50a08138e8c47d943335124ae88d3397", "parents": [ "505cc4e1d6885acaee008950ac9c6e838f2209f8" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:42:23 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:11 2006 -0800" }, "message": "[PATCH] x86_64: Adjust page fault handling\n\nAdjust page fault protection error check before considering it to be\na vmalloc synchronization candidate.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "505cc4e1d6885acaee008950ac9c6e838f2209f8", "tree": "068e4d458f02003853d7d9a1a8a6b72338222f94", "parents": [ "eca37c18beb306dd9dea4579d7214e1b4414b3fb" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:42:20 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:10 2006 -0800" }, "message": "[PATCH] x86_64: Remove unprotected iret\n\nMake sure no iret can fault without attached recovery code.\nCannot happen in the normal case, but might be useful\nwith kernel debuggers\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "eca37c18beb306dd9dea4579d7214e1b4414b3fb", "tree": "f74aecdd6f793dd01901220e4a09e82c021d7028", "parents": [ "6e3f361781573a27296c77a79c9892dec8f2e36c" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:42:17 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:10 2006 -0800" }, "message": "[PATCH] x86_64: Clean up double fault handling\n\nSince a double fault always implies that kernel data structures are\ncorrupt, this fault should neither be handed to user mode handling,\nnor should the handler allow resuming the faulting code stream (since\narchitecturally this isn\u0027t a fault, but an abort).\n\nNote that this slightly depends on the previously submitted patch\nadjusting the prototype of notify_die() (a compiler warning will result\nwithout that other patch).\n\nAK: Removed obsolete CONFIG_CHECKING code, added comments\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6e3f361781573a27296c77a79c9892dec8f2e36c", "tree": "b08ff3ed470d0e21ce3d462f16d6d3f0a6965a9c", "parents": [ "5c617cfa6422bfba9e79d8d004303a6cc3d2e7d7" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:42:14 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:10 2006 -0800" }, "message": "[PATCH] x86_64: make trap information available to die notification handlers\n\nThis adjusts things so that handlers of the die() notifier will have\nsufficient information about the trap currently being handled. It also\nadjusts the notify_die() prototype to (again) match that of i386.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "5c617cfa6422bfba9e79d8d004303a6cc3d2e7d7", "tree": "c60f411ef40c648b06fff8e8fca286fcaa868f48", "parents": [ "0a5215882166dd33a95b313637dd318e4c143113" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:42:11 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:10 2006 -0800" }, "message": "[PATCH] x86_64: Removing unused function die_if_kernel().\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "0a5215882166dd33a95b313637dd318e4c143113", "tree": "00b3211382219459ddebdc8bcde2f3881a657b08", "parents": [ "6e0c47ede7b1473a4e2ab65a0fecf0385ab23c03" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:42:08 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:10 2006 -0800" }, "message": "[PATCH] x86_64: fix bound check IDT gate\n\nOther than apparently commonly assumed, the bound instruction does not\nrequire the corresponding IDT entry to have DPL 3.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6e0c47ede7b1473a4e2ab65a0fecf0385ab23c03", "tree": "b190f8d76776faf5a2fba9fbfa866c71ec793265", "parents": [ "130951ccb14167c20b87e8bed52b60864ed53c2b" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:42:05 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:10 2006 -0800" }, "message": "[PATCH] x86_64: Separate CONFIG_UNWIND_INFO from CONFIG_DEBUG_INFO\n\nAs a follow-up to the introduction of CONFIG_UNWIND_INFO, this\nseparates the generation of frame unwind information for x86-64 from\nthat of full debug information.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" } ], "next": "130951ccb14167c20b87e8bed52b60864ed53c2b" }